CN101794371A - Method for adjusting light source threshold value of face identification - Google Patents

Abstract

A method for adjusting a light source threshold value of face recognition comprises the steps of shooting an input image; calculating a first luminance value of an input image; loading a target image; loading a second brightness value of the target image; comparing the first brightness value with the second brightness value to obtain a brightness difference value between the input image and the target image; adjusting the basic threshold value according to the brightness difference value to obtain an identification threshold value; and performing a face recognition procedure on the input image by using the recognition threshold.

Description

Method for adjusting light source threshold for face recognition

technical field

The invention relates to a face recognition method, in particular to a method for adjusting a light source threshold for face recognition.

Background technique

In the face recognition technology, the user's face only needs to be within the effective shooting distance of the electronic device with image capture function, and the face recognition process can be performed after the electronic device captures the user's face image.

Since facial recognition is applied to electronic devices, it is the result of a series of calculations and image numerical calculations performed by the electronic devices. The electronic device compares and calculates a value according to the user's input image and the target image in the storage device. This value is used to represent the image similarity value of the user in face recognition. In addition, a basic threshold is set in the electronic device, which is used as a standard for judging whether the image similarity value passes the recognition in the face recognition program.

Usually, the input image of the user extracted by the electronic device will be too different from the actual user's face image due to the difference of the ambient light source. Because the external ambient light source will affect the change of the light and shadow of the user's face, the calculated image similarity value will fluctuate too much. As a result, the image similarity value cannot meet the standard of the basic threshold, so that the user cannot pass the identification. Therefore, the face recognition program of the electronic device is often affected by the ambient light source, which reduces the recognition effect and brings a lot of inconvenience to the user's operation.

Contents of the invention

In view of the above problems, the present invention provides a method for adjusting the light source threshold of face recognition, so as to dynamically adjust the basic threshold of face recognition under different ambient light sources.

Therefore, the method for adjusting the light source threshold for face recognition disclosed in the present invention includes: taking an input image; calculating the first brightness value of the input image; loading the target image; loading the second brightness value of the target image; comparing the first the brightness value and the second brightness value to obtain a brightness difference value between the input image and the target image; adjust the basic threshold according to the brightness difference value to obtain a recognition threshold; and use the recognition threshold to perform a face recognition process on the input image.

Wherein, the first brightness value may include a brightness average value and a brightness standard deviation value of the input image, and the second brightness value may include a brightness average value and a brightness standard deviation value of the target image.

In addition, the average brightness of the input image can be calculated using the following formula: $\stackrel{\‾}{x}=\frac{1}{N}\underset{i=1}{\overset{N}{\∑}}{x}_i.$

为输入图像的亮度平均值、N为输入图像的像素总数、i为输入图像的第i个像素、x_i为输入图像的第i个像素的亮度值、且N与i为正整数。In this calculation,

is the average brightness of the input image, N is the total number of pixels of the input image, i is the i-th pixel of the input image, x _i is the brightness value of the i-th pixel of the input image, and N and i are positive integers.

Moreover, the average brightness of the target image can be calculated using the following formula: $\stackrel{\‾}{\mathrm{the\; y}}=\frac{1}{m}\underset{j=1}{\overset{m}{\∑}}{\mathrm{the\; y}}_j.$

为目标图像的亮度平均值、M为目标图像的像素总数、j为目标图像的第j个像素、y_j为目标图像的第j个像素的亮度值、且M与j为正整数。In this calculation,

is the average brightness of the target image, M is the total number of pixels of the target image, j is the jth pixel of the target image, _yj is the brightness value of the jth pixel of the target image, and M and j are positive integers.

In addition, the brightness standard deviation value of the input image can be calculated using the following formula:

$\mathrm{<span\; class="notranslate">\; \&sigma;</span>}<span\; class="notranslate">\; =</span>\sqrt{\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{<span\; class="notranslate">\; \&Sum;</span>}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; .</span>$

为输入图像的亮度平均值、且N与i为正整数。In this calculation formula, σ is the brightness standard deviation value of the input image, N is the total number of pixels of the input image, i is the i-th pixel of the input image, x _i is the brightness value of the i-th pixel of the input image,

is the average brightness of the input image, and N and i are positive integers.

And, the brightness standard deviation value of the target image can be calculated using the following formula:

$\mathrm{<span\; class="notranslate">\; \&theta;</span>}<span\; class="notranslate">\; =</span>\sqrt{\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; m</span>}}\underset{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; m</span>}}{<span\; class="notranslate">\; \&Sum;</span>}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; .</span>$

为目标图像的亮度平均值、且M与j为正整数。In this calculation formula, θ is the brightness standard deviation value of the target image, M is the total number of pixels of the target image, j is the jth pixel of the target image, y _j is the brightness value of the jth pixel of the target image,

is the average brightness of the target image, and M and j are positive integers.

In addition, before the step of loading the target image and the step of loading the second brightness value of the target image corresponding to the target image, it may further include: shooting the target image; calculating the second brightness value of the captured target image; and storing The captured target image and the calculated second brightness value.

In addition, the step of comparing the first brightness value with the second brightness value to obtain the brightness difference value between the input image and the target image may include: comparing the brightness average value in the first brightness value with the brightness in the second brightness value average value to obtain the first difference value; compare the brightness standard deviation value of the first brightness value with the brightness standard deviation value of the second brightness value to obtain the second difference value; and calculate the input according to the first difference value and the second difference value The brightness difference value between the image and the target image.

In addition, the step of adjusting the basic threshold according to the brightness difference value to obtain the identification threshold may include: looking up the first lookup table according to the brightness difference value to obtain the first compensation value corresponding to the brightness difference value; looking up the second lookup table according to the brightness difference value to obtain a second compensation value corresponding to the brightness difference value; calculate a threshold compensation value according to the first compensation value and the second compensation value; and adjust the basic threshold with the threshold compensation value to obtain a recognition threshold.

Wherein, the step of calculating the compensation threshold according to the first compensation value and the second compensation value may include: accumulating the first compensation value and the second compensation value to obtain the compensation threshold.

Here, the first compensation value is related to the average brightness of the input image, and the second compensation value is related to the standard deviation of brightness of the input image.

In addition, before the step of adjusting the basic threshold, it may further include: setting the basic threshold.

Finally, the face recognition program may include: detecting the first face block in the input image; detecting the second face block in the target image; calculating the detected first face block and the detected second face block block to obtain the image similarity value; and compare the recognition threshold with the image similarity value to determine whether the input image passes the face recognition process.

According to the method for adjusting the light source threshold for face recognition provided by the present invention, when applied to a face recognition system, the recognition threshold used for face recognition can be dynamically adjusted under different light sources. Regardless of the environment with poor light or the brightness difference of images recorded in the database is too large, the recognition threshold can be raised or lowered appropriately. This allows users to successfully complete facial recognition in different environments and under different lighting conditions.

Regarding the characteristics and implementation of the present invention, the best embodiment is described in detail below in conjunction with the drawings.

Description of drawings

FIG. 1 is a flow chart of a method for adjusting a light source threshold for face recognition according to an embodiment of the present invention.

FIG. 2 is a detailed flow chart of an embodiment of a shooting target image in a method for adjusting a light source threshold for face recognition according to the present invention.

3 is a detailed flow chart of comparing brightness difference values between an input image and a target image according to an embodiment of the method for adjusting a light source threshold for face recognition according to the present invention.

FIG. 4 is a detailed flowchart of an embodiment of adjusting a basic threshold to obtain a recognition threshold in the method for adjusting a light source threshold for face recognition according to the present invention.

5 is a detailed flow chart of calculating the compensation threshold according to an embodiment of the method for adjusting the light source threshold for face recognition according to the present invention.

FIG. 6 is a detailed flow chart of a face recognition program according to an embodiment of the method for adjusting a light source threshold for face recognition according to the present invention.

Detailed ways

The method for adjusting the light source threshold for face recognition according to the present invention is applied to an electronic device with image extraction function. This method can be built into the storage device of the electronic device through software or firmware program, and then the processor of the electronic device executes the built-in software or firmware program together with the image extraction function to realize the light source threshold value of face recognition according to the present invention. Adjustment method. Here, the electronic device can be a computer (Computer) with image extraction function, a mobile phone (Mobile Phone) with image extraction function, or a personal digital assistant (Personal Digital Assistant, PDA) with image extraction function, etc., but not limited to the aforementioned electronic devices.

In this application, the basic threshold is dynamically adjusted to obtain the recognition threshold by comparing the brightness difference between the input image and the target image, and then the face recognition process of the input image is performed using the obtained recognition threshold.

Please refer to FIG. 1 , which is a flowchart of a method for adjusting a light source threshold for face recognition according to an embodiment of the present invention.

When the electronic device receives a face recognition instruction, firstly, the electronic device captures an input image (step S110 ), and calculates a first brightness value of the captured input image (step S120 ). Then, the electronic device loads the target image from the storage device (step S130 ), and loads the second brightness value of the target image (step S140 ). Comparing the first luminance value and the second luminance value to obtain a luminance difference value between the input image and the target image (step S150 ). At this time, the basic threshold is adjusted according to the brightness difference value to obtain the recognition threshold (step S160). Finally, a face recognition process is performed on the input image by using the recognition threshold (step S170).

Wherein, the first brightness value includes an average brightness value and a brightness standard deviation value of the input image, and the second brightness value includes an average brightness value and a brightness standard deviation value of the target image.

Here, the average brightness of the input image can be calculated using the following formula: $\stackrel{\&OverBar;}{x}=\frac{1}{N}\underset{i=1}{\overset{N}{\&Sum;}}{x}_i.$

为输入图像的亮度平均值、N为输入图像的像素总数、i为输入图像的第i个像素、x_i为输入图像的第i个像素的亮度值、且N与i为正整数。in,

is the average brightness of the input image, N is the total number of pixels of the input image, i is the i-th pixel of the input image, x _i is the brightness value of the i-th pixel of the input image, and N and i are positive integers.

Moreover, the average brightness of the target image can be calculated using the following formula: $\stackrel{\&OverBar;}{\mathrm{the\; y}}=\frac{1}{m}\underset{j=1}{\overset{m}{\&Sum;}}{\mathrm{the\; y}}_j.$

为目标图像的亮度平均值、M为目标图像的像素总数、j为目标图像的第j个像素、y_j为目标图像的第j个像素的亮度值、且M与j为正整数。in,

is the average brightness of the target image, M is the total number of pixels of the target image, j is the jth pixel of the target image, _yj is the brightness value of the jth pixel of the target image, and M and j are positive integers.

In addition, the brightness standard deviation value of the input image can be calculated using the following formula:

$\mathrm{<span\; class="notranslate">\; \&sigma;</span>}<span\; class="notranslate">\; =</span>\sqrt{\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{<span\; class="notranslate">\; \&Sum;</span>}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; .</span>$

为输入图像的亮度平均值、且N与i为正整数。Among them, σ is the brightness standard deviation value of the input image, N is the total number of pixels of the input image, i is the i-th pixel of the input image, x _i is the brightness value of the i-th pixel of the input image,

is the average brightness of the input image, and N and i are positive integers.

And, the brightness standard deviation value of the target image can be calculated using the following formula:

$\mathrm{<span\; class="notranslate">\; \&theta;</span>}<span\; class="notranslate">\; =</span>\sqrt{\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; m</span>}}\underset{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; m</span>}}{<span\; class="notranslate">\; \&Sum;</span>}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; .</span>$

为目标图像的亮度平均值、且M与j为正整数。Among them, θ is the brightness standard deviation value of the target image, M is the total number of pixels of the target image, j is the jth pixel of the target image, y _j is the brightness value of the jth pixel of the target image,

is the average brightness of the target image, and M and j are positive integers.

Here, before step S130 and step S140, the following implementation steps may be further included.

Please refer to "FIG. 2", first, the electronic device captures a target image (step S210), and calculates a second brightness value of the captured target image (step S220). Then the electronic device stores the photographed target image and the calculated second brightness value in the storage device (step S230).

Here, the average brightness of the target image can be calculated using the following formula: $\stackrel{\&OverBar;}{\mathrm{the\; y}}=\frac{1}{m}\underset{j=1}{\overset{m}{\&Sum;}}{\mathrm{the\; y}}_j.$

为目标图像的亮度平均值、M为目标图像的像素总数、j为目标图像的第j个像素、y_j为目标图像的第y个像素的亮度值、且M与j为正整数。in,

is the average brightness of the target image, M is the total number of pixels of the target image, j is the jth pixel of the target image, y _j is the brightness value of the yth pixel of the target image, and M and j are positive integers.

And, the brightness standard deviation value of the target image can be calculated using the following formula:

$\mathrm{<span\; class="notranslate">\; \&theta;</span>}<span\; class="notranslate">\; =</span>\sqrt{\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; m</span>}}\underset{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; m</span>}}{<span\; class="notranslate">\; \&Sum;</span>}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}<span\; class="notranslate">\; .</span>$

为目标图像的亮度平均值、且M与j为正整数。Among them, θ is the brightness standard deviation value of the target image, M is the total number of pixels of the target image, j is the jth pixel of the target image, y _j is the brightness value of the jth pixel of the target image,

is the average brightness of the target image, and M and j are positive integers.

In addition, for step S150, the following implementation steps may be included.

Please refer to "FIG. 3", first, compare the brightness average value in the first brightness value with the brightness average value in the second brightness value to obtain a first difference value (step S152). Then, compare the brightness standard deviation value of the first brightness value with the brightness standard deviation value of the second brightness value to obtain a second difference value (step S154 ). Finally, the brightness difference value between the input image and the target image is calculated according to the first difference value and the second difference value (step S156 ).

In addition, for step S160, the following implementation steps may be included.

Please refer to "FIG. 4", firstly, look up the first lookup table according to the brightness difference value to obtain the first compensation value corresponding to the brightness difference value (step S162). Then, look up the second lookup table according to the brightness difference value to obtain a second compensation value corresponding to the brightness difference value (step S164 ). And, a threshold compensation value is calculated according to the first compensation value and the second compensation value (step S166). Finally, adjust the basic threshold with the threshold compensation value to obtain the identification threshold (step S168).

"Table 1" is a first look-up table according to an embodiment of the present invention, which is the first compensation value corresponding to the first difference value among the brightness difference values. "Table 2" is the second lookup table according to the embodiment of the present invention, which is the second compensation value corresponding to the second difference value in the brightness difference value.

Table I

Table II

Wherein, for step S166, the following implementation steps may be included.

Please refer to "FIG. 5", the first compensation value and the second compensation value are accumulated to obtain the compensation threshold (step S167).

In addition, the first compensation value is related to the average brightness of the input image, and the second compensation value is related to the standard deviation of brightness of the input image.

In addition, the electronic device can preset a basic threshold, which is used as a comparison with the brightness difference between the input image and the target image during the execution of the face recognition program.

Finally, for step S170, the following implementation steps may be included.

Please refer to "FIG. 6", firstly, detect the first face block in the input image (step S172). Then, detect the second face block in the target image (step S174). Calculate the detected first face block and the detected second face block to obtain an image similarity value (step S176). Finally, compare the recognition threshold with the image similarity value to determine whether the input image passes the face recognition process (step S178).

For example, when the electronic device receives a face recognition instruction, the electronic device first captures an input image, and calculates a first brightness value of the captured input image. For the convenience of description here, it is assumed that the average brightness value in the first brightness value is 64, and the standard deviation value in the first brightness value is 18. Then, the electronic device loads the target image from the storage device, and loads the second brightness value of the target image. For the convenience of description here, it is assumed that the average value of brightness in the second brightness value is 86, and the standard deviation value in the second brightness value is 33. The brightness average 64 in the first brightness value is compared with the brightness average 86 in the second brightness value to obtain a first difference value 64−86=−22. And, compare the brightness standard deviation value 18 of the first brightness value with the brightness standard deviation value 33 of the second brightness value to obtain a second difference value 18−33=−15. Finally, the brightness difference value between the input image and the target image is calculated according to the first difference value −22 and the second difference value −15 (22, 15).

According to the first difference value 22 in the brightness difference value (22, 15), the first compensation value corresponding to the brightness difference value can be obtained as 0.5 of item 2 by looking up "Table 1". And, according to the first difference value 15 in the brightness difference value lookup (22, 15), the second compensation value corresponding to the brightness difference value can be obtained by looking up "Table 2", which is 3.0 of item 3. Then, the sum of the first compensation value 0.5 and the second compensation value 3.0 is calculated to obtain the threshold compensation value 3.5. Finally, the recognition threshold can be obtained by adjusting the basic threshold with a threshold compensation value of 3.5, and then the face recognition process can be performed on the input image by using the recognition threshold.

In this embodiment, two input images and target images with different brightness are used as illustrations. However, in the actual application of the facial recognition program, multiple target images can be loaded into the storage device of the electronic device. The input image is used to perform face recognition with multiple target images, so as to determine whether the input image passes the face recognition process.

According to the method for adjusting the light source threshold for face recognition provided by the present invention, when applied to a face recognition system, the recognition threshold used for face recognition can be dynamically adjusted under different light sources. Regardless of the environment with poor light or the brightness difference of images recorded in the database is too large, the recognition threshold can be raised or lowered appropriately. This allows users to successfully complete facial recognition in different environments and under different lighting conditions.

Although the present invention is disclosed above with the aforementioned preferred embodiments, it is not intended to limit the present invention. Those skilled in the art may make some changes and modifications without departing from the spirit and scope of the present invention. Therefore, the present invention The scope of patent protection shall be defined by the claims attached to this specification.

Claims (15)

1. A method for adjusting a light source threshold for face recognition, comprising: taking an input image; calculating a first brightness value of the input image; load a target image; loading a second brightness value of the target image; comparing the first brightness value with the second brightness value to obtain a brightness difference value between the input image and the target image; adjusting a basic threshold according to the brightness difference value to obtain a recognition threshold; and A face recognition process is performed on the input image by using the recognition threshold. 2. The method for adjusting the light source threshold for face recognition as claimed in claim 1, wherein the first brightness value includes a brightness average value and a brightness standard deviation value of the input image, and the second brightness value includes the target A brightness average value and a brightness standard deviation value of the image. 3. The method for adjusting the light source threshold for face recognition as claimed in claim 2, wherein the average brightness value of the input image is calculated using the following formula: $\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}$ in,

is the brightness average value of the input image, N is the total number of pixels of the input image, i is the i-th pixel of the input image, x _i is the brightness value of the i-th pixel of the input image, and N and i is a positive integer. 4. The method for adjusting the light source threshold of face recognition as claimed in claim 3, wherein the average brightness of the target image is calculated by the following formula: $\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; m</span>}}\underset{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; m</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}$ in,

is the brightness average value of the target image, M is the total number of pixels of the target image, j is the jth pixel of the target image, y _j is the brightness value of the jth pixel of the target image, and M and j is a positive integer. 5. The method for adjusting the light source threshold for face recognition as claimed in claim 2, wherein the brightness standard deviation value of the input image is calculated using the following formula: $\mathrm{<span\; class="notranslate">\; \&sigma;</span>}<span\; class="notranslate">\; =</span>\sqrt{\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; N</span>}}\underset{\mathrm{<span\; class="notranslate">\; i</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; N</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; x</span>}}_{\mathrm{<span\; class="notranslate">\; i</span>}}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; x</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}$ Wherein, σ is the brightness standard deviation value of the input image, N is the total number of pixels of the input image, i is the i-th pixel of the input image, x _i is the brightness value of the i-th pixel of the input image,

is the average brightness value of the input image, and N and i are positive integers. 6. The method for adjusting the light source threshold for face recognition as claimed in claim 5, wherein the brightness standard deviation value of the target image is calculated using the following formula: $\mathrm{<span\; class="notranslate">\; \&theta;</span>}<span\; class="notranslate">\; =</span>\sqrt{\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; m</span>}}\underset{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; m</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}$ Wherein, θ is the brightness standard deviation value of the target image, M is the total number of pixels of the target image, j is the jth pixel of the target image, and _yj is the brightness value of the jth pixel of the target image,

is the average brightness of the target image, and M and j are positive integers. 7. The method for adjusting the light source threshold for face recognition according to claim 1, wherein before the step of loading the target image and before the step of loading the second brightness value of the target image corresponding to the target image ,Also includes: taking the target image; calculating the second brightness value of the captured image of the target; and The captured target image and the calculated second brightness value are stored. 8. The method for adjusting the light source threshold of face recognition as claimed in claim 7, wherein the average brightness of the target image is calculated by using the following formula: $\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; =</span>\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; m</span>}}\underset{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; m</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}$ in,

is the brightness average value of the target image, M is the total number of pixels of the target image, j is the jth pixel of the target image, y _j is the brightness value of the yth pixel of the target image, and M and j is a positive integer. 9. The method for adjusting the light source threshold of face recognition as claimed in claim 7, wherein the brightness standard deviation value of the target image is calculated using the following formula: $\mathrm{<span\; class="notranslate">\; \&theta;</span>}<span\; class="notranslate">\; =</span>\sqrt{\frac{\mathrm{<span\; class="notranslate">\; 1</span>}}{\mathrm{<span\; class="notranslate">\; m</span>}}\underset{\mathrm{<span\; class="notranslate">\; j</span>}<span\; class="notranslate">\; =</span>\mathrm{<span\; class="notranslate">\; 1</span>}}{\overset{\mathrm{<span\; class="notranslate">\; m</span>}}{\mathrm{<span\; class="notranslate">\; \&Sigma;</span>}}}{<span\; class="notranslate">\; (</span>{\mathrm{<span\; class="notranslate">\; the\; y</span>}}_{\mathrm{<span\; class="notranslate">\; j</span>}}<span\; class="notranslate">\; -</span>\stackrel{<span\; class="notranslate">\; \&OverBar;</span>}{\mathrm{<span\; class="notranslate">\; the\; y</span>}}<span\; class="notranslate">\; )</span>}^{\mathrm{<span\; class="notranslate">\; 2</span>}}}$ Wherein, θ is the brightness standard deviation value of the target image, M is the total number of pixels of the target image, j is the jth pixel of the target image, and _yj is the brightness value of the jth pixel of the target image,

is the average brightness of the target image, and M and j are positive integers. 10. The method for adjusting the light source threshold for face recognition as claimed in claim 1, wherein the step of comparing the first brightness value and the second brightness value to obtain the brightness difference value between the input image and the target image ,include: comparing a luminance average value of the first luminance value with a luminance average value of the second luminance value to obtain a first difference value; comparing a brightness standard deviation value of the first brightness value with a brightness standard deviation value of the second brightness value to obtain a second difference value; and The brightness difference value between the input image and the target image is calculated according to the first difference value and the second difference value. 11. The method for adjusting the light source threshold for face recognition as claimed in claim 1, wherein the step of adjusting the basic threshold to obtain the recognition threshold according to the brightness difference value comprises: searching a first look-up table according to the brightness difference value to obtain a first compensation value corresponding to the brightness difference value; searching the second lookup table according to the brightness difference value to obtain a second compensation value corresponding to the brightness difference value; calculating a threshold compensation value according to the first compensation value and the second compensation value; and The basic threshold is adjusted with the threshold compensation value to obtain the identification threshold. 12. The method for adjusting the light source threshold for face recognition as claimed in claim 1, wherein the step of calculating the compensation threshold according to the first compensation value and the second compensation value comprises: Accumulate the first compensation value and the second compensation value to obtain the compensation threshold. 13. The method for adjusting the light source threshold for face recognition as claimed in claim 1, wherein the first compensation value is related to an average brightness of the input image, and the second compensation value is related to a brightness of the input image standard deviation. 14. The method for adjusting the light source threshold for face recognition as claimed in claim 1, wherein before the step of adjusting the basic threshold, further comprising: Set the base threshold. 15. The method for adjusting the light source threshold of face recognition as claimed in claim 1, wherein the face recognition program comprises: detecting a first face block in the input image; detecting a second face block in the target image; calculating the detected first face block and the detected second face block to obtain an image similarity value; and The recognition threshold is compared with the image similarity value to determine whether the input image passes the face recognition process.

Images